ClawHub
Back to skill

Security audit

Linear 工具箱

Security checks across malware telemetry and agentic risk

Overview

This Linear skill is broadly coherent, but it can change live Linear workspace data and its trigger/safety boundaries are too loose.

Install only if you want the agent to operate on your Linear workspace. Use a limited-scope Linear API key where possible, treat create/update/comment/assign/delete-style actions as live changes, and ask the agent to confirm before any write operation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger condition '需要项目管理、任务规划、进度跟踪、团队协作时使用' is broad enough to activate this skill for many generic planning requests, even when the user did not intend to operate on Linear. In an MD+EXEC skill with remote task-management capabilities, over-broad routing increases the chance of unintended invocation and downstream state-changing actions against a live Linear workspace.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill advertises create/query/modify/delete/export/save style operations and task updates/comments, but it does not clearly warn users that these actions may change remote Linear data. In combination with exec-enabled agent execution, this can lead to accidental mutation of production task data, audit noise, unwanted comments/status changes, or destructive actions if the agent infers permission to proceed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.